Since load_idx effect removed in load balance, we don't need the load_idx decays in scheduler. that will save some time in sched_tick and others places.

Signed-off-by: Alex Shi alex.shi@linaro.org --- arch/ia64/include/asm/topology.h | 5 --- arch/metag/include/asm/topology.h | 5 --- arch/tile/include/asm/topology.h | 6 --- include/linux/sched.h | 5 --- include/linux/topology.h | 8 ---- kernel/sched/core.c | 60 ++++++++----------------- kernel/sched/debug.c | 6 +-- kernel/sched/fair.c | 79 +++++++++------------------------ kernel/sched/proc.c | 92 ++------------------------------------- kernel/sched/sched.h | 3 +- 10 files changed, 43 insertions(+), 226 deletions(-)

diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h index a2496e4..54e5b17 100644 --- a/arch/ia64/include/asm/topology.h +++ b/arch/ia64/include/asm/topology.h @@ -55,11 +55,6 @@ void build_cpu_to_node_map(void); .busy_factor = 64, \ .imbalance_pct = 125, \ .cache_nice_tries = 2, \ - .busy_idx = 2, \ - .idle_idx = 1, \ - .newidle_idx = 0, \ - .wake_idx = 0, \ - .forkexec_idx = 0, \ .flags = SD_LOAD_BALANCE \ | SD_BALANCE_NEWIDLE \ | SD_BALANCE_EXEC \ diff --git a/arch/metag/include/asm/topology.h b/arch/metag/include/asm/topology.h index 8e9c0b3..d1d15cd 100644 --- a/arch/metag/include/asm/topology.h +++ b/arch/metag/include/asm/topology.h @@ -13,11 +13,6 @@ .busy_factor = 32, \ .imbalance_pct = 125, \ .cache_nice_tries = 2, \ - .busy_idx = 3, \ - .idle_idx = 2, \ - .newidle_idx = 0, \ - .wake_idx = 0, \ - .forkexec_idx = 0, \ .flags = SD_LOAD_BALANCE \ | SD_BALANCE_FORK \ | SD_BALANCE_EXEC \ diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h index d15c0d8..05f6ffe 100644 --- a/arch/tile/include/asm/topology.h +++ b/arch/tile/include/asm/topology.h @@ -57,12 +57,6 @@ static inline const struct cpumask *cpumask_of_node(int node) .busy_factor = 64, \ .imbalance_pct = 125, \ .cache_nice_tries = 1, \ - .busy_idx = 2, \ - .idle_idx = 1, \ - .newidle_idx = 0, \ - .wake_idx = 0, \ - .forkexec_idx = 0, \ - \ .flags = 1*SD_LOAD_BALANCE \ | 1*SD_BALANCE_NEWIDLE \ | 1*SD_BALANCE_EXEC \ diff --git a/include/linux/sched.h b/include/linux/sched.h index 7e35d4b..a23e02d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -815,11 +815,6 @@ struct sched_domain { unsigned int busy_factor; /* less balancing by factor if busy */ unsigned int imbalance_pct; /* No balance until over watermark */ unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */ - unsigned int busy_idx; - unsigned int idle_idx; - unsigned int newidle_idx; - unsigned int wake_idx; - unsigned int forkexec_idx; unsigned int smt_gain;

int nohz_idle; /* NOHZ IDLE status */ diff --git a/include/linux/topology.h b/include/linux/topology.h index 12ae6ce..863fad3 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -121,9 +121,6 @@ int arch_update_cpu_topology(void); .busy_factor = 64, \ .imbalance_pct = 125, \ .cache_nice_tries = 1, \ - .busy_idx = 2, \ - .wake_idx = 0, \ - .forkexec_idx = 0, \ \ .flags = 1*SD_LOAD_BALANCE \ | 1*SD_BALANCE_NEWIDLE \ @@ -151,11 +148,6 @@ int arch_update_cpu_topology(void); .busy_factor = 64, \ .imbalance_pct = 125, \ .cache_nice_tries = 1, \ - .busy_idx = 2, \ - .idle_idx = 1, \ - .newidle_idx = 0, \ - .wake_idx = 0, \ - .forkexec_idx = 0, \ \ .flags = 1*SD_LOAD_BALANCE \ | 1*SD_BALANCE_NEWIDLE \ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c180860..9528f75 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4279,61 +4279,42 @@ static void sd_free_ctl_entry(struct ctl_table **tablep) *tablep = NULL; }

-static int min_load_idx = 0; -static int max_load_idx = CPU_LOAD_IDX_MAX-1; - static void set_table_entry(struct ctl_table *entry, const char *procname, void *data, int maxlen, - umode_t mode, proc_handler *proc_handler, - bool load_idx) + umode_t mode, proc_handler *proc_handler) { entry->procname = procname; entry->data = data; entry->maxlen = maxlen; entry->mode = mode; entry->proc_handler = proc_handler; - - if (load_idx) { - entry->extra1 = &min_load_idx; - entry->extra2 = &max_load_idx; - } }

static struct ctl_table * sd_alloc_ctl_domain_table(struct sched_domain *sd) { - struct ctl_table *table = sd_alloc_ctl_entry(13); + struct ctl_table *table = sd_alloc_ctl_entry(8);

if (table == NULL) return NULL;

set_table_entry(&table[0], "min_interval", &sd->min_interval, - sizeof(long), 0644, proc_doulongvec_minmax, false); + sizeof(long), 0644, proc_doulongvec_minmax); set_table_entry(&table[1], "max_interval", &sd->max_interval, - sizeof(long), 0644, proc_doulongvec_minmax, false); - set_table_entry(&table[2], "busy_idx", &sd->busy_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[3], "idle_idx", &sd->idle_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[5], "wake_idx", &sd->wake_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[7], "busy_factor", &sd->busy_factor, - sizeof(int), 0644, proc_dointvec_minmax, false); - set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, - sizeof(int), 0644, proc_dointvec_minmax, false); - set_table_entry(&table[9], "cache_nice_tries", + sizeof(long), 0644, proc_doulongvec_minmax); + set_table_entry(&table[2], "busy_factor", &sd->busy_factor, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[3], "imbalance_pct", &sd->imbalance_pct, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[4], "cache_nice_tries", &sd->cache_nice_tries, - sizeof(int), 0644, proc_dointvec_minmax, false); - set_table_entry(&table[10], "flags", &sd->flags, - sizeof(int), 0644, proc_dointvec_minmax, false); - set_table_entry(&table[11], "name", sd->name, - CORENAME_MAX_SIZE, 0444, proc_dostring, false); - /* &table[12] is terminator */ + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[5], "flags", &sd->flags, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[6], "name", sd->name, + CORENAME_MAX_SIZE, 0444, proc_dostring); + /* &table[7] is terminator */

return table; } @@ -5425,11 +5406,6 @@ sd_numa_init(struct sched_domain_topology_level *tl, int cpu) .busy_factor = 32, .imbalance_pct = 125, .cache_nice_tries = 2, - .busy_idx = 3, - .idle_idx = 2, - .newidle_idx = 0, - .wake_idx = 0, - .forkexec_idx = 0,

.flags = 1*SD_LOAD_BALANCE | 1*SD_BALANCE_NEWIDLE @@ -6178,7 +6154,7 @@ DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);

void __init sched_init(void) { - int i, j; + int i; unsigned long alloc_size = 0, ptr;

#ifdef CONFIG_FAIR_GROUP_SCHED @@ -6279,9 +6255,7 @@ void __init sched_init(void) init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL); #endif

- for (j = 0; j < CPU_LOAD_IDX_MAX; j++) - rq->cpu_load[j] = 0; - + rq->cpu_load = 0; rq->last_load_update_tick = jiffies;

#ifdef CONFIG_SMP diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 5c34d18..675be71 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -303,11 +303,7 @@ do { \ PN(next_balance); SEQ_printf(m, " .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr))); PN(clock); - P(cpu_load[0]); - P(cpu_load[1]); - P(cpu_load[2]); - P(cpu_load[3]); - P(cpu_load[4]); + P(cpu_load); #undef P #undef PN

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ce683aa..bccdd89 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -977,8 +977,8 @@ static inline unsigned long group_weight(struct task_struct *p, int nid) }

static unsigned long weighted_cpuload(const int cpu); -static unsigned long source_load(int cpu, int type); -static unsigned long target_load(int cpu, int type); +static unsigned long source_load(int cpu); +static unsigned long target_load(int cpu); static unsigned long power_of(int cpu); static long effective_load(struct task_group *tg, int cpu, long wl, long wg);

@@ -3794,30 +3794,30 @@ static unsigned long weighted_cpuload(const int cpu) * We want to under-estimate the load of migration sources, to * balance conservatively. */ -static unsigned long source_load(int cpu, int type) +static unsigned long source_load(int cpu) { struct rq *rq = cpu_rq(cpu); unsigned long total = weighted_cpuload(cpu);

- if (type == 0 || !sched_feat(LB_BIAS)) + if (!sched_feat(LB_BIAS)) return total;

- return min(rq->cpu_load[type-1], total); + return min(rq->cpu_load, total); }

/* * Return a high guess at the load of a migration-target cpu weighted * according to the scheduling class and "nice" value. */ -static unsigned long target_load(int cpu, int type) +static unsigned long target_load(int cpu) { struct rq *rq = cpu_rq(cpu); unsigned long total = weighted_cpuload(cpu);

- if (type == 0 || !sched_feat(LB_BIAS)) + if (!sched_feat(LB_BIAS)) return total;

- return max(rq->cpu_load[type-1], total); + return max(rq->cpu_load, total); }

static unsigned long power_of(int cpu) @@ -4017,7 +4017,7 @@ static int wake_wide(struct task_struct *p) static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) { s64 this_load, load; - int idx, this_cpu, prev_cpu; + int this_cpu, prev_cpu; unsigned long tl_per_task; struct task_group *tg; unsigned long weight; @@ -4030,11 +4030,10 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) if (wake_wide(p)) return 0;

- idx = sd->wake_idx; this_cpu = smp_processor_id(); prev_cpu = task_cpu(p); - load = source_load(prev_cpu, idx); - this_load = target_load(this_cpu, idx); + load = source_load(prev_cpu); + this_load = target_load(this_cpu);

/* * If sync wakeup then subtract the (maximum possible) @@ -4090,7 +4089,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)

if (balanced || (this_load <= load && - this_load + target_load(prev_cpu, idx) <= tl_per_task)) { + this_load + target_load(prev_cpu) <= tl_per_task)) { /* * This domain has SD_WAKE_AFFINE and * p is cache cold in this domain, and @@ -4109,8 +4108,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) * domain. */ static struct sched_group * -find_idlest_group(struct sched_domain *sd, struct task_struct *p, - int this_cpu, int load_idx) +find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) { struct sched_group *idlest = NULL, *group = sd->groups; unsigned long min_load = ULONG_MAX, this_load = 0; @@ -4135,9 +4133,9 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, for_each_cpu(i, sched_group_cpus(group)) { /* Bias balancing toward cpus of our domain */ if (local_group) - load = source_load(i, load_idx); + load = source_load(i); else - load = target_load(i, load_idx); + load = target_load(i);

avg_load += load; } @@ -4283,7 +4281,6 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f }

while (sd) { - int load_idx = sd->forkexec_idx; struct sched_group *group; int weight;

@@ -4292,10 +4289,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f continue; }

- if (sd_flag & SD_BALANCE_WAKE) - load_idx = sd->wake_idx; - - group = find_idlest_group(sd, p, cpu, load_idx); + group = find_idlest_group(sd, p, cpu); if (!group) { sd = sd->child; continue; @@ -5238,34 +5232,6 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds) }; }

-/** - * get_sd_load_idx - Obtain the load index for a given sched domain. - * @sd: The sched_domain whose load_idx is to be obtained. - * @idle: The idle status of the CPU for whose sd load_idx is obtained. - * - * Return: The load index. - */ -static inline int get_sd_load_idx(struct sched_domain *sd, - enum cpu_idle_type idle) -{ - int load_idx; - - switch (idle) { - case CPU_NOT_IDLE: - load_idx = sd->busy_idx; - break; - - case CPU_NEWLY_IDLE: - load_idx = sd->newidle_idx; - break; - default: - load_idx = sd->idle_idx; - break; - } - - return load_idx; -} - static unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) { return SCHED_POWER_SCALE; @@ -5492,12 +5458,11 @@ static inline int sg_capacity(struct lb_env *env, struct sched_group *group) * update_sg_lb_stats - Update sched_group's statistics for load balancing. * @env: The load balancing environment. * @group: sched_group whose statistics are to be updated. - * @load_idx: Load index of sched_domain of this_cpu for load calc. * @local_group: Does group contain this_cpu. * @sgs: variable to hold the statistics for this group. */ static inline void update_sg_lb_stats(struct lb_env *env, - struct sched_group *group, int load_idx, + struct sched_group *group, int local_group, struct sg_lb_stats *sgs) { unsigned long nr_running; @@ -5513,9 +5478,9 @@ static inline void update_sg_lb_stats(struct lb_env *env,

/* Bias balancing toward cpus of our domain */ if (local_group) - load = target_load(i, load_idx); + load = target_load(i); else - load = source_load(i, load_idx); + load = source_load(i);

sgs->group_load += load; sgs->sum_nr_running += nr_running; @@ -5628,13 +5593,11 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd struct sched_domain *child = env->sd->child; struct sched_group *sg = env->sd->groups; struct sg_lb_stats tmp_sgs; - int load_idx, prefer_sibling = 0; + int prefer_sibling = 0;

if (child && child->flags & SD_PREFER_SIBLING) prefer_sibling = 1;

- load_idx = 0; - do { struct sg_lb_stats *sgs = &tmp_sgs; int local_group; @@ -5649,7 +5612,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd update_group_power(env->sd, env->dst_cpu); }

- update_sg_lb_stats(env, sg, load_idx, local_group, sgs); + update_sg_lb_stats(env, sg, local_group, sgs);

if (local_group) goto next_group; diff --git a/kernel/sched/proc.c b/kernel/sched/proc.c index 16f5a30..a2435c5 100644 --- a/kernel/sched/proc.c +++ b/kernel/sched/proc.c @@ -11,7 +11,7 @@ unsigned long this_cpu_load(void) { struct rq *this = this_rq(); - return this->cpu_load[0]; + return this->cpu_load; }

@@ -398,105 +398,19 @@ static void calc_load_account_active(struct rq *this_rq) * End of global load-average stuff */

-/* - * The exact cpuload at various idx values, calculated at every tick would be - * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load - * - * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called - * on nth tick when cpu may be busy, then we have: - * load = ((2^idx - 1) / 2^idx)^(n-1) * load - * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load - * - * decay_load_missed() below does efficient calculation of - * load = ((2^idx - 1) / 2^idx)^(n-1) * load - * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load - * - * The calculation is approximated on a 128 point scale. - * degrade_zero_ticks is the number of ticks after which load at any - * particular idx is approximated to be zero. - * degrade_factor is a precomputed table, a row for each load idx. - * Each column corresponds to degradation factor for a power of two ticks, - * based on 128 point scale. - * Example: - * row 2, col 3 (=12) says that the degradation at load idx 2 after - * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8). - * - * With this power of 2 load factors, we can degrade the load n times - * by looking at 1 bits in n and doing as many mult/shift instead of - * n mult/shifts needed by the exact degradation. - */ -#define DEGRADE_SHIFT 7 -static const unsigned char - degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128}; -static const unsigned char - degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = { - {0, 0, 0, 0, 0, 0, 0, 0}, - {64, 32, 8, 0, 0, 0, 0, 0}, - {96, 72, 40, 12, 1, 0, 0}, - {112, 98, 75, 43, 15, 1, 0}, - {120, 112, 98, 76, 45, 16, 2} };

/* - * Update cpu_load for any missed ticks, due to tickless idle. The backlog - * would be when CPU is idle and so we just decay the old load without - * adding any new load. - */ -static unsigned long -decay_load_missed(unsigned long load, unsigned long missed_updates, int idx) -{ - int j = 0; - - if (!missed_updates) - return load; - - if (missed_updates >= degrade_zero_ticks[idx]) - return 0; - - if (idx == 1) - return load >> missed_updates; - - while (missed_updates) { - if (missed_updates % 2) - load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT; - - missed_updates >>= 1; - j++; - } - return load; -} - -/* - * Update rq->cpu_load[] statistics. This function is usually called every + * Update rq->cpu_load statistics. This function is usually called every * scheduler tick (TICK_NSEC). With tickless idle this will not be called * every tick. We fix it up based on jiffies. */ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, unsigned long pending_updates) { - int i, scale; - this_rq->nr_load_updates++;

/* Update our load: */ - this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */ - for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { - unsigned long old_load, new_load; - - /* scale is effectively 1 << i now, and >> i divides by scale */ - - old_load = this_rq->cpu_load[i]; - old_load = decay_load_missed(old_load, pending_updates - 1, i); - new_load = this_load; - /* - * Round up the averaging division if load is increasing. This - * prevents us from getting stuck on 9 if the load is 10, for - * example. - */ - if (new_load > old_load) - new_load += scale - 1; - - this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i; - } + this_rq->cpu_load = this_load; /* Fasttrack for idx 0 */

sched_avg_update(this_rq); } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 88c85b2..01f6e7a 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -413,8 +413,7 @@ struct rq { unsigned int nr_numa_running; unsigned int nr_preferred_running; #endif - #define CPU_LOAD_IDX_MAX 5 - unsigned long cpu_load[CPU_LOAD_IDX_MAX]; + unsigned long cpu_load; unsigned long last_load_update_tick; #ifdef CONFIG_NO_HZ_COMMON u64 nohz_stamp;

When a nohz_full cpu in tickless mode, it may update cpu_load in following chain: __tick_nohz_full_check tick_nohz_restart_sched_tick update_cpu_load_nohz then it will be set a incorrect cpu_load: 0. This patch try to fix it and give it the correct cpu_load value.

Signed-off-by: Alex Shi alex.shi@linaro.org --- kernel/sched/proc.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/proc.c b/kernel/sched/proc.c index 057bb9b..5058e6a 100644 --- a/kernel/sched/proc.c +++ b/kernel/sched/proc.c @@ -477,10 +477,16 @@ void update_cpu_load_nohz(void) if (pending_updates) { this_rq->last_load_update_tick = curr_jiffies; /* - * We were idle, this means load 0, the current load might be - * !0 due to remote wakeups and the sort. + * We may has one task and in NO_HZ_FULL, then use normal + * cfs load. + * Or we were idle, this means load 0, the current load might + * be !0 due to remote wakeups and the sort. */ - __update_cpu_load(this_rq, 0); + if (this_rq->cfs.h_nr_running) { + unsigned load = get_rq_runnable_load(this_rq); + __update_cpu_load(this_rq, load); + } else + __update_cpu_load(this_rq, 0); } raw_spin_unlock(&this_rq->lock); }